2 citations · 2 across the 3 of their papers we have counts for
3 papers
From Pointwise to Powerhouse: Initialising Neural Networks with Generative Models
Christian Harder, Moritz Fuchs, Yuri Tolkach +1
Traditional initialisation methods, e.g. He and Xavier, have been effective in avoiding the problem of vanishing or exploding gradients in neural networks. However, they only use s…
Jointly Exploring Client Drift and Catastrophic Forgetting in Dynamic Learning
Niklas Babendererde, Moritz Fuchs, Camila Gonzalez +2
Federated and Continual Learning have emerged as potential paradigms for the robust and privacy-aware use of Deep Learning in dynamic environments. However, Client Drift and Catast…
Critical Evaluation of Artificial Intelligence as Digital Twin of Pathologist for Prostate Cancer Pathology
Okyaz Eminaga, Mahmoud Abbas, Christian Kunder +10
Prostate cancer pathology plays a crucial role in clinical management but is time-consuming. Artificial intelligence (AI) shows promise in detecting prostate cancer and grading pat…